ai tools finished

backend/services/audio_cleaner.py

@@ -7,23 +7,52 @@ import logging
 import re
 import subprocess
 import tempfile
+import warnings
 from pathlib import Path
 
 logger = logging.getLogger(__name__)
 
-try:
-    from df.enhance import enhance, init_df, load_audio, save_audio
-    DEEPFILTER_AVAILABLE = True
-except ImportError:
-    DEEPFILTER_AVAILABLE = False
+DEEPFILTER_AVAILABLE = None
+enhance = None
+init_df = None
+load_audio = None
+save_audio = None
 
 
 _df_model = None
 _df_state = None
 
 
+def _ensure_deepfilter_loaded() -> bool:
+    global DEEPFILTER_AVAILABLE, enhance, init_df, load_audio, save_audio
+    if DEEPFILTER_AVAILABLE is not None:
+        return DEEPFILTER_AVAILABLE
+
+    try:
+        # DeepFilterNet currently triggers a third-party torchaudio deprecation warning
+        # on import in some environments; suppress only this known warning.
+        with warnings.catch_warnings():
+            warnings.filterwarnings(
+                "ignore",
+                message=r".*torchaudio\._backend\.common\.AudioMetaData has been moved.*",
+                category=UserWarning,
+            )
+            from df.enhance import enhance as _enhance, init_df as _init_df, load_audio as _load_audio, save_audio as _save_audio
+        enhance = _enhance
+        init_df = _init_df
+        load_audio = _load_audio
+        save_audio = _save_audio
+        DEEPFILTER_AVAILABLE = True
+    except ImportError:
+        DEEPFILTER_AVAILABLE = False
+
+    return DEEPFILTER_AVAILABLE
+
+
 def _init_deepfilter():
     global _df_model, _df_state
+    if not _ensure_deepfilter_loaded():
+        raise RuntimeError("DeepFilterNet is not available")
     if _df_model is None:
         logger.info("Initializing DeepFilterNet model")
         _df_model, _df_state, _ = init_df()
@@ -46,7 +75,7 @@ def clean_audio(
     if not output_path:
         output_path = str(input_path.with_stem(input_path.stem + "_clean"))
 
-    if DEEPFILTER_AVAILABLE:
+    if is_deepfilter_available():
         return _clean_with_deepfilter(str(input_path), output_path)
     else:
         return _clean_with_ffmpeg(str(input_path), output_path)
@@ -77,7 +106,7 @@ def _clean_with_ffmpeg(input_path: str, output_path: str) -> str:
 
 
 def is_deepfilter_available() -> bool:
-    return DEEPFILTER_AVAILABLE
+    return _ensure_deepfilter_loaded()
 
 
 def detect_silence_ranges(input_path: str, min_silence_ms: int, silence_db: float):